Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225706887> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4225706887 abstract "Traditional deep learning interpretability methods which are suitable for non-expert users cannot explain network behaviors at the global level and are inflexible at providing fine-grained explanations. As a solution, concept-based explanations are gaining attention due to their human intuitiveness and their flexibility to describe both global and local model behaviors. Concepts are groups of similarly meaningful pixels that express a notion, embedded within the network's latent space and have primarily been hand-generated, but have recently been discovered by automated approaches. Unfortunately, the magnitude and diversity of discovered concepts makes it difficult for non-experts to navigate and make sense of the concept space, and lack of easy-to-use software also makes concept explanations inaccessible to many non-expert users. Visual analytics can serve a valuable role in bridging these gaps by enabling structured navigation and exploration of the concept space to provide concept-based insights of model behavior to users. To this end, we design, develop, and validate ConceptExplainer, a visual analytics system that enables non-expert users to interactively probe and explore the concept space to explain model behavior at the instance/class/global level. The system was developed via iterative prototyping to address a number of design challenges that non-experts face in interpreting the behavior of deep learning models. Via a rigorous user study, we validate how ConceptExplainer supports these challenges. Likewise, we conduct a series of usage scenarios to demonstrate how the system supports the interactive analysis of model behavior across a variety of tasks and explanation granularities, such as identifying concepts that are important to classification, identifying bias in training data, and understanding how concepts can be shared across diverse and seemingly dissimilar classes." @default.
- W4225706887 created "2022-05-05" @default.
- W4225706887 creator A5002316828 @default.
- W4225706887 creator A5032388678 @default.
- W4225706887 creator A5043391973 @default.
- W4225706887 creator A5057053812 @default.
- W4225706887 date "2022-04-04" @default.
- W4225706887 modified "2023-10-11" @default.
- W4225706887 title "ConceptExplainer: Understanding the Mental Model of Deep Learning Algorithms via Interactive Concept-based Explanations" @default.
- W4225706887 hasPublicationYear "2022" @default.
- W4225706887 type Work @default.
- W4225706887 citedByCount "0" @default.
- W4225706887 crossrefType "posted-content" @default.
- W4225706887 hasAuthorship W4225706887A5002316828 @default.
- W4225706887 hasAuthorship W4225706887A5032388678 @default.
- W4225706887 hasAuthorship W4225706887A5043391973 @default.
- W4225706887 hasAuthorship W4225706887A5057053812 @default.
- W4225706887 hasBestOaLocation W42257068871 @default.
- W4225706887 hasConcept C105795698 @default.
- W4225706887 hasConcept C107457646 @default.
- W4225706887 hasConcept C111919701 @default.
- W4225706887 hasConcept C119857082 @default.
- W4225706887 hasConcept C136197465 @default.
- W4225706887 hasConcept C154945302 @default.
- W4225706887 hasConcept C174348530 @default.
- W4225706887 hasConcept C2522767166 @default.
- W4225706887 hasConcept C2778572836 @default.
- W4225706887 hasConcept C2780598303 @default.
- W4225706887 hasConcept C2781067378 @default.
- W4225706887 hasConcept C31258907 @default.
- W4225706887 hasConcept C33923547 @default.
- W4225706887 hasConcept C36464697 @default.
- W4225706887 hasConcept C41008148 @default.
- W4225706887 hasConcept C59732488 @default.
- W4225706887 hasConcept C79158427 @default.
- W4225706887 hasConceptScore W4225706887C105795698 @default.
- W4225706887 hasConceptScore W4225706887C107457646 @default.
- W4225706887 hasConceptScore W4225706887C111919701 @default.
- W4225706887 hasConceptScore W4225706887C119857082 @default.
- W4225706887 hasConceptScore W4225706887C136197465 @default.
- W4225706887 hasConceptScore W4225706887C154945302 @default.
- W4225706887 hasConceptScore W4225706887C174348530 @default.
- W4225706887 hasConceptScore W4225706887C2522767166 @default.
- W4225706887 hasConceptScore W4225706887C2778572836 @default.
- W4225706887 hasConceptScore W4225706887C2780598303 @default.
- W4225706887 hasConceptScore W4225706887C2781067378 @default.
- W4225706887 hasConceptScore W4225706887C31258907 @default.
- W4225706887 hasConceptScore W4225706887C33923547 @default.
- W4225706887 hasConceptScore W4225706887C36464697 @default.
- W4225706887 hasConceptScore W4225706887C41008148 @default.
- W4225706887 hasConceptScore W4225706887C59732488 @default.
- W4225706887 hasConceptScore W4225706887C79158427 @default.
- W4225706887 hasLocation W42257068871 @default.
- W4225706887 hasOpenAccess W4225706887 @default.
- W4225706887 hasPrimaryLocation W42257068871 @default.
- W4225706887 hasRelatedWork W11104910 @default.
- W4225706887 hasRelatedWork W1195902 @default.
- W4225706887 hasRelatedWork W1466306 @default.
- W4225706887 hasRelatedWork W15595896 @default.
- W4225706887 hasRelatedWork W17483448 @default.
- W4225706887 hasRelatedWork W24270 @default.
- W4225706887 hasRelatedWork W3563469 @default.
- W4225706887 hasRelatedWork W573916 @default.
- W4225706887 hasRelatedWork W630684 @default.
- W4225706887 hasRelatedWork W10290560 @default.
- W4225706887 isParatext "false" @default.
- W4225706887 isRetracted "false" @default.
- W4225706887 workType "article" @default.